Web scraping, crawling & search for AI agents.
Scrape, crawl, search, and extract the live web (plus domain intelligence and browser automation) behind one API key, one bill, and one MCP server. Most calls cost 1 credit, JS rendering costs nothing extra, refund on failure.
curl https://api.ollagraph.com/v1/scrape/llm-ready \
-H "Authorization: Bearer $OLLAGRAPH_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"url": "https://en.wikipedia.org/wiki/Web_scraping",
"max_tokens": 512,
"overlap_tokens": 64
}'
{
"status": "success",
"url": "https://en.wikipedia.org/wiki/Web_scraping",
"title": "Web scraping - Wikipedia",
"rendered_with_js": false,
"rendered_via": "direct",
"chunks": [
{
"text": "Web scraping is the process of automatically extracting data from websites…",
"token_count": 498,
"byte_start": 0,
"byte_end": 2196
},
{ /* chunk 2, 3, 4, 5 */ }
]
}
SPA detection automatically escalates to a residential rendering pool when needed. Identical response
schema; rendered_with_js
flags which path served the call.
Most endpoints cost 1 credit; search, screenshots, and full page audits cost 3. If an upstream fetch fails, your balance is refunded automatically before returning.
Every endpoint doubles as an MCP tool. Run pipx run ollagraph-mcp
to give Claude Desktop & Cursor all 123 tools at once.
Credits are auto-refunded immediately before returning if an upstream target blocks or fails.
We never cache, persist, or train on your scraped content. Data streams straight to your runtime.
Financially backed uptime guarantees with priority redundant routing across edge proxies.
Access scrape, crawl, search, structured extraction, and intel behind a single auth and bill.
Emits W3C traceparent, Server-Timing, and standard IETF draft rate-limit headers on all responses.
One platform. The whole web stack.
The core web-data primitives (scrape, crawl, search, and extract) behind a single auth, a single bill, and one MCP server. No more duct-taping a scraper, a SERP, a parser, and a headless browser.
Smart crawling
Render-aware crawls that follow links, respect robots, and bypass anti-bot walls cleanly.
Web search
Search the live web across engines, merged and deduped by URL, ranked results from one call, no SERP scraping to maintain.
Structured extraction
Structured extraction with JSON schemas, retries, and verification, typed end-to-end.
Agent observability
Every call logged with URL, status, latency, and credits. Forward traces to your own OpenTelemetry collector.
Browser automation
Render JS-heavy pages, click, type, scroll, and evaluate JavaScript. Every call is a fresh, stateless browser.
AEO audits
Audit how AI crawlers see, cite, and rank your site. Get a remediation checklist instantly.
Markdown conversion
Clean, model-ready markdown for any page. Strips chrome, keeps semantics, preserves citations.
Async jobs
Async scrape, batch, and crawl jobs with webhooks and idempotency keys. Poll any job by ID.
One endpoint.
One auth. One billing.
A plain REST API with a published OpenAPI spec: call it with fetch, requests, or curl. Idempotent jobs, webhooks, and structured errors. Built the way you wished scraping APIs were built ten years ago.
Typed everywhere
Every request and response is described in the OpenAPI spec, with examples.
Async by default
Long crawls and batches run as jobs: poll the job ID or get a webhook when they finish.
Per-request visibility
Look up any call by request ID; usage and credits broken down per key.
// Crawl a site as an async job, then poll it until it finishes.
const headers = {
Authorization: `Bearer ${process.env.OLLAGRAPH_API_KEY}`,
"Content-Type": "application/json",
};
const { job_id } = await (await fetch("https://api.ollagraph.com/v1/crawl", {
method: "POST",
headers,
body: JSON.stringify({
url: "https://news.ycombinator.com",
max_pages: 50,
depth: 2,
}),
})).json();
let job;
do {
await new Promise((r) => setTimeout(r, 5000));
job = await (await fetch(`https://api.ollagraph.com/v1/jobs/${job_id}`, { headers })).json();
} while (job.status !== "completed" && job.status !== "failed");
console.log(job.status, job.result);
One API, built for what agents actually do.
From RAG ingestion to lead enrichment, price monitoring, and AI-search audits: the same key, the same credits.
/v1/scrape/llm-ready
RAG & LLM pipelines
Turn any site or document into clean, chunked, model-ready markdown for retrieval, embeddings, and context ingestion.
/v1/intel/page
Sales & lead intelligence
Enrich domains into verified contacts, tech stack fingerprints, and firmographics for prospecting and automated RevOps.
/v1/extract/structured
Price & review monitoring
Track competitor SKUs, pricing variants, stock status, and sentiment reviews across marketplaces on an automated schedule.
/v1/aeo/citation-readiness
SEO & AEO audits
Audit how search engines and AI answer engines (ChatGPT, Perplexity, Claude) see, parse, cite, and rank your content.
Priced for how agents actually run.
Most calls cost 1 credit (search and screenshots cost 3); no JS render multiplier, so a JavaScript-rendered page costs the same as a static one. Pay as you go from $5, get refunded automatically when a fetch fails, and start with 1,000 free credits.
|
Benchmark
How It Compares
|
Recommended
OLLAGRAPH
Unified agent web stack
|
Baseline
FIRECRAWL
Markdown context API
|
Alternatives
TYPICAL SCRAPING API
ScraperAPI, ScrapingBee, etc.
|
|---|---|---|---|
|
Price per call
Static HTML or dynamic JS rendering
|
1 credit
Zero JS render multiplier
|
1–5× by feature
Multipliers for JS & actions
|
Per-request tiers
Separate residential & JS fees
|
|
Pay-as-you-go from $5
Spend only what you need, no lock-in
|
Yes, from $5
Credits never expire
|
No
Subscription plans only
|
Varies
Usually $29–$49/mo minimums
|
|
Refund on failed fetch
Automatic credit restoration on 4xx/5xx
|
Yes, 100% auto
Zero charge on failed fetches
|
No
Charged even on 403 / 404
|
No
Billed per request attempt
|
|
Free to start
Credits granted upfront to evaluate platform
|
1,000 credits
All 147 endpoints, no card
|
500 credits
Basic crawl allotment
|
Trial only
Time-limited or strict caps
|
|
MCP server included
Native Model Context Protocol for AI agents
|
Yes, native
pipx run ollagraph-mcp
|
Yes
Base MCP implementation
|
No
Requires custom wrappers
|
|
Unified API surface
Search + crawl + extract + intelligence, one key
|
Yes, all-in-one
Web, DNS, SERP, & AEO
|
Scrape + crawl
Search requires separate add-on
|
Scrape only
No SERP, DNS, or AI reasoning
|
|
Zero content retention
Enterprise data privacy guarantee for agents
|
Yes, guaranteed
Never stored, cached, or trained on
|
Cached / Retained
Short-term caching & logs
|
Varies / Retained
Proxy logs & response caches
|
Where Ollagraph pulls ahead: JavaScript rendering without multipliers
On raw static HTML, a few providers match our entry rate. Where Ollagraph separates is real-world, JavaScript-rendered pages: 1 credit per scrape with zero render multipliers, true pay-as-you-go from $5, automated refund-on-failure, and the largest free tier.
Built for teams at scale.
Governance, controls & dedicated throughput.
Volume pricing, an uptime SLA, SCIM, SAML, and fine-grained RBAC, plus the data-handling guarantee that matters for agent workloads: we never persist scraped content. For teams who need to know exactly where their data goes.
Built on open web standards: we honor the Robots Exclusion Protocol (RFC 9309), extract W3C JSON-LD structured data, and follow the sitemaps and robots.txt conventions the whole web already relies on.
Questions, answered.
Everything you need to know about pricing, data retention, MCP integration, and agent infrastructure.
Have a specific or edge-case question?
Can't find what you're looking for? Reach out directly to protocol engineering or inspect our interactive documentation.
01
How
does Ollagraph compare to Firecrawl?
02
Is there a free tier and pay-as-you-go pricing?
03
How is Ollagraph priced and metered?
04
Does Ollagraph provide an MCP server for AI agents?
pipx run ollagraph-mcp to instantly expose all 123 tools directly to Claude Desktop, Cursor, or your custom Model Context Protocol client with full schema typing.
05
Do you store the content Ollagraph scrapes?
06
Is Ollagraph a good Firecrawl alternative?
Ship agents that actually understand the web.
Start with 1,000 credits. No credit card required. Production-ready in five minutes through one unified API and native MCP server your autonomous systems will never outgrow.